str.c revision 1.56
1 /* $NetBSD: str.c,v 1.56 2020/08/09 10:24:02 rillig Exp $ */ 2 3 /*- 4 * Copyright (c) 1988, 1989, 1990, 1993 5 * The Regents of the University of California. All rights reserved. 6 * 7 * This code is derived from software contributed to Berkeley by 8 * Adam de Boor. 9 * 10 * Redistribution and use in source and binary forms, with or without 11 * modification, are permitted provided that the following conditions 12 * are met: 13 * 1. Redistributions of source code must retain the above copyright 14 * notice, this list of conditions and the following disclaimer. 15 * 2. Redistributions in binary form must reproduce the above copyright 16 * notice, this list of conditions and the following disclaimer in the 17 * documentation and/or other materials provided with the distribution. 18 * 3. Neither the name of the University nor the names of its contributors 19 * may be used to endorse or promote products derived from this software 20 * without specific prior written permission. 21 * 22 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 23 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 24 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 25 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 26 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 27 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 28 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 29 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 30 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 31 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 32 * SUCH DAMAGE. 33 */ 34 35 /*- 36 * Copyright (c) 1989 by Berkeley Softworks 37 * All rights reserved. 38 * 39 * This code is derived from software contributed to Berkeley by 40 * Adam de Boor. 41 * 42 * Redistribution and use in source and binary forms, with or without 43 * modification, are permitted provided that the following conditions 44 * are met: 45 * 1. Redistributions of source code must retain the above copyright 46 * notice, this list of conditions and the following disclaimer. 47 * 2. Redistributions in binary form must reproduce the above copyright 48 * notice, this list of conditions and the following disclaimer in the 49 * documentation and/or other materials provided with the distribution. 50 * 3. All advertising materials mentioning features or use of this software 51 * must display the following acknowledgement: 52 * This product includes software developed by the University of 53 * California, Berkeley and its contributors. 54 * 4. Neither the name of the University nor the names of its contributors 55 * may be used to endorse or promote products derived from this software 56 * without specific prior written permission. 57 * 58 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 59 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 60 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 61 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 62 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 63 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 64 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 65 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 66 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 67 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 68 * SUCH DAMAGE. 69 */ 70 71 #ifndef MAKE_NATIVE 72 static char rcsid[] = "$NetBSD: str.c,v 1.56 2020/08/09 10:24:02 rillig Exp $"; 73 #else 74 #include <sys/cdefs.h> 75 #ifndef lint 76 #if 0 77 static char sccsid[] = "@(#)str.c 5.8 (Berkeley) 6/1/90"; 78 #else 79 __RCSID("$NetBSD: str.c,v 1.56 2020/08/09 10:24:02 rillig Exp $"); 80 #endif 81 #endif /* not lint */ 82 #endif 83 84 #include "make.h" 85 86 /*- 87 * str_concat -- 88 * concatenate the two strings, inserting a space or slash between them, 89 * freeing them if requested. 90 * 91 * returns -- 92 * the resulting string in allocated space. 93 */ 94 char * 95 str_concat(const char *s1, const char *s2, int flags) 96 { 97 int len1, len2; 98 char *result; 99 100 /* get the length of both strings */ 101 len1 = strlen(s1); 102 len2 = strlen(s2); 103 104 /* allocate length plus separator plus EOS */ 105 result = bmake_malloc((unsigned int)(len1 + len2 + 2)); 106 107 /* copy first string into place */ 108 memcpy(result, s1, len1); 109 110 /* add separator character */ 111 if (flags & STR_ADDSPACE) { 112 result[len1] = ' '; 113 ++len1; 114 } else if (flags & STR_ADDSLASH) { 115 result[len1] = '/'; 116 ++len1; 117 } 118 119 /* copy second string plus EOS into place */ 120 memcpy(result + len1, s2, len2 + 1); 121 122 return result; 123 } 124 125 /*- 126 * brk_string -- 127 * Fracture a string into an array of words (as delineated by tabs or 128 * spaces) taking quotation marks into account. Leading tabs/spaces 129 * are ignored. 130 * 131 * If expand is TRUE, quotes are removed and escape sequences 132 * such as \r, \t, etc... are expanded. In this case, the return value 133 * is NULL on parse errors. 134 * 135 * returns -- 136 * Pointer to the array of pointers to the words. 137 * Memory containing the actual words in *out_words_buf. 138 * Both of these must be free'd by the caller. 139 * Number of words in *out_words_len. 140 */ 141 char ** 142 brk_string(const char *str, int *out_words_len, Boolean expand, 143 char **out_words_buf) 144 { 145 size_t str_len; 146 char *words_buf; 147 int words_cap; 148 char **words; 149 int words_len; 150 char inquote; 151 char *word_start; 152 char *word_end; 153 const char *str_p; 154 155 /* skip leading space chars. */ 156 for (; *str == ' ' || *str == '\t'; ++str) 157 continue; 158 159 /* words_buf holds the words, separated by '\0'. */ 160 str_len = strlen(str); 161 words_buf = bmake_malloc(strlen(str) + 1); 162 163 words_cap = MAX((str_len / 5), 50); 164 words = bmake_malloc((words_cap + 1) * sizeof(char *)); 165 166 /* 167 * copy the string; at the same time, parse backslashes, 168 * quotes and build the word list. 169 */ 170 words_len = 0; 171 inquote = '\0'; 172 word_start = words_buf; 173 word_end = words_buf; 174 for (str_p = str;; ++str_p) { 175 char ch = *str_p; 176 switch (ch) { 177 case '"': 178 case '\'': 179 if (inquote) { 180 if (inquote == ch) 181 inquote = '\0'; 182 else 183 break; 184 } else { 185 inquote = (char)ch; 186 /* Don't miss "" or '' */ 187 if (word_start == NULL && str_p[1] == inquote) { 188 if (!expand) { 189 word_start = word_end; 190 *word_end++ = ch; 191 } else 192 word_start = word_end + 1; 193 str_p++; 194 inquote = '\0'; 195 break; 196 } 197 } 198 if (!expand) { 199 if (word_start == NULL) 200 word_start = word_end; 201 *word_end++ = ch; 202 } 203 continue; 204 case ' ': 205 case '\t': 206 case '\n': 207 if (inquote) 208 break; 209 if (word_start == NULL) 210 continue; 211 /* FALLTHROUGH */ 212 case '\0': 213 /* 214 * end of a token -- make sure there's enough words 215 * space and save off a pointer. 216 */ 217 if (word_start == NULL) 218 goto done; 219 220 *word_end++ = '\0'; 221 if (words_len == words_cap) { 222 size_t new_size; 223 words_cap *= 2; /* ramp up fast */ 224 new_size = (words_cap + 1) * sizeof(char *); 225 words = bmake_realloc(words, new_size); 226 } 227 words[words_len++] = word_start; 228 word_start = NULL; 229 if (ch == '\n' || ch == '\0') { 230 if (expand && inquote) { 231 free(words); 232 free(words_buf); 233 *out_words_buf = NULL; 234 return NULL; 235 } 236 goto done; 237 } 238 continue; 239 case '\\': 240 if (!expand) { 241 if (word_start == NULL) 242 word_start = word_end; 243 *word_end++ = '\\'; 244 /* catch '\' at end of line */ 245 if (str_p[1] == '\0') 246 continue; 247 ch = *++str_p; 248 break; 249 } 250 251 switch (ch = *++str_p) { 252 case '\0': 253 case '\n': 254 /* hmmm; fix it up as best we can */ 255 ch = '\\'; 256 --str_p; 257 break; 258 case 'b': 259 ch = '\b'; 260 break; 261 case 'f': 262 ch = '\f'; 263 break; 264 case 'n': 265 ch = '\n'; 266 break; 267 case 'r': 268 ch = '\r'; 269 break; 270 case 't': 271 ch = '\t'; 272 break; 273 } 274 break; 275 } 276 if (word_start == NULL) 277 word_start = word_end; 278 *word_end++ = ch; 279 } 280 done: 281 words[words_len] = NULL; 282 *out_words_len = words_len; 283 *out_words_buf = words_buf; 284 return words; 285 } 286 287 /* 288 * Str_FindSubstring -- See if a string contains a particular substring. 289 * 290 * Input: 291 * string String to search. 292 * substring Substring to find in string. 293 * 294 * Results: If string contains substring, the return value is the location of 295 * the first matching instance of substring in string. If string doesn't 296 * contain substring, the return value is NULL. Matching is done on an exact 297 * character-for-character basis with no wildcards or special characters. 298 * 299 * Side effects: None. 300 */ 301 char * 302 Str_FindSubstring(const char *string, const char *substring) 303 { 304 const char *a, *b; 305 306 /* 307 * First scan quickly through the two strings looking for a single- 308 * character match. When it's found, then compare the rest of the 309 * substring. 310 */ 311 312 for (b = substring; *string != 0; string++) { 313 if (*string != *b) 314 continue; 315 a = string; 316 for (;;) { 317 if (*b == 0) 318 return UNCONST(string); 319 if (*a++ != *b++) 320 break; 321 } 322 b = substring; 323 } 324 return NULL; 325 } 326 327 /* 328 * Str_Match -- Test if a string matches a pattern like "*.[ch]". 329 * 330 * XXX this function does not detect or report malformed patterns. 331 * 332 * Results: 333 * Non-zero is returned if string matches the pattern, 0 otherwise. The 334 * matching operation permits the following special characters in the 335 * pattern: *?\[] (as in fnmatch(3)). 336 * 337 * Side effects: None. 338 */ 339 Boolean 340 Str_Match(const char *str, const char *pat) 341 { 342 for (;;) { 343 /* 344 * See if we're at the end of both the pattern and the 345 * string. If, we succeeded. If we're at the end of the 346 * pattern but not at the end of the string, we failed. 347 */ 348 if (*pat == 0) 349 return *str == 0; 350 if (*str == 0 && *pat != '*') 351 return FALSE; 352 353 /* 354 * A '*' in the pattern matches any substring. We handle this 355 * by calling ourselves for each suffix of the string. 356 */ 357 if (*pat == '*') { 358 pat++; 359 while (*pat == '*') 360 pat++; 361 if (*pat == 0) 362 return TRUE; 363 while (*str != 0) { 364 if (Str_Match(str, pat)) 365 return TRUE; 366 str++; 367 } 368 return FALSE; 369 } 370 371 /* A '?' in the pattern matches any single character. */ 372 if (*pat == '?') 373 goto thisCharOK; 374 375 /* 376 * A '[' in the pattern matches a character from a list. 377 * The '[' is followed by the list of acceptable characters, 378 * or by ranges (two characters separated by '-'). In these 379 * character lists, the backslash is an ordinary character. 380 */ 381 if (*pat == '[') { 382 Boolean neg = pat[1] == '^'; 383 pat += 1 + neg; 384 385 for (;;) { 386 if (*pat == ']' || *pat == 0) { 387 if (neg) 388 break; 389 return FALSE; 390 } 391 if (*pat == *str) 392 break; 393 if (pat[1] == '-') { 394 if (pat[2] == 0) 395 return neg; 396 if (*pat <= *str && pat[2] >= *str) 397 break; 398 if (*pat >= *str && pat[2] <= *str) 399 break; 400 pat += 2; 401 } 402 pat++; 403 } 404 if (neg && *pat != ']' && *pat != 0) 405 return FALSE; 406 while (*pat != ']' && *pat != 0) 407 pat++; 408 if (*pat == 0) 409 pat--; 410 goto thisCharOK; 411 } 412 413 /* 414 * A backslash in the pattern matches the character following 415 * it exactly. 416 */ 417 if (*pat == '\\') { 418 pat++; 419 if (*pat == 0) 420 return FALSE; 421 } 422 423 if (*pat != *str) 424 return FALSE; 425 426 thisCharOK: 427 pat++; 428 str++; 429 } 430 } 431
Indexes created Mon Sep 22 13:09:51 GMT 2025